Artificial intelligence-based generator / motor design device and method thereof

Abstract

Disclosed are an artificial intelligence-based generator / motor design device and a method thereof. That is, the present invention generates structural variable data of a plurality of generators / motors, performs artificial intelligence-based machine learning on the basis of the generated structural variable data of the plurality of generators / motors, generates performance evaluation data for each piece of structural variable data of the plurality of generators / motors on the basis of a machine learning result, predicts the structural specifications of the generators / motors by applying a genetic algorithm on the basis of reverse design input data of the generators / motors generated from user inputs and the previously generated performance evaluation data for each piece of structural variable data of the plurality of generators / motors, evaluates performance, for a sample manufactured through 3D printing, on the basis of the predicted structural specifications of the generators / motors, and manufactures a prototype according to the performance evaluation result, thus making it possible to save time and costs incurred by actual experiments and manufacture a variety of generators / motors on the basis of artificial intelligence.

Description

Artificial intelligence-based generator / motor design device and method thereof

[0001] The present invention relates to an artificial intelligence-based generator / motor design device and method thereof, and more particularly, to an artificial intelligence-based generator / motor design device and method thereof, which generates structural variable data of a plurality of generators / motors, performs artificial intelligence-based machine learning based on the generated structural variable data of the plurality of generators / motors, generates performance evaluation data for each structural variable data of the plurality of generators / motors based on the machine learning results, applies a genetic algorithm based on reverse engineering input data of the generator / motor according to user input and the previously generated performance evaluation data for each structural variable data of the plurality of generators / motors, predicts the structural specifications of the generator / motor, evaluates the performance of a sample manufactured through 3D printing based on the predicted structural specifications of the generator / motor, and manufactures a prototype based on the performance evaluation results.

[0002] Due to environmental concerns worldwide, efforts are being made to strengthen environmental regulations across industries and develop new, eco-friendly energy sources to reduce greenhouse gas emissions. These environmental regulations and the development of eco-friendly energy sources must be accompanied by increased efficiency in the use of existing energy sources.

[0003] Generators and motors are among the most promising options for optimizing energy efficiency. Despite their long history, these technologies require diverse designs due to differences in specifications applied across industries and the volume and scale of energy sources (nuclear, fossil fuel, hydrogen, solar, solar thermal, wind, fuel cells, etc.).

[0004] An object of the present invention is to provide an artificial intelligence-based generator / motor design device and method, which generate structural variable data of a plurality of generators / motors, perform artificial intelligence-based machine learning based on the generated structural variable data of the plurality of generators / motors, generate performance evaluation data for each structural variable data of the plurality of generators / motors based on the machine learning results, apply a genetic algorithm based on reverse engineering input data of the generator / motor according to user input and the previously generated performance evaluation data for each structural variable data of the plurality of generators / motors, predict the structural specifications of the generator / motor, evaluate the performance of a sample manufactured through 3D printing based on the predicted structural specifications of the generator / motor, and manufacture a prototype based on the performance evaluation results.

[0005] An AI-based generator / motor design device according to an embodiment of the present invention may include: a storage unit that stores performance evaluation data for each structural variable data of a plurality of generators / motors; and a control unit that applies a genetic algorithm to predict predicted structural specifications of a generator / motor based on reverse engineering input data of a generator / motor according to a user input and performance evaluation data for each structural variable data of the plurality of generators / motors, and, in conjunction with a 3D printer, manufactures a generator / motor sample based on the predicted structural specifications of the generator / motor, calculates accuracy for the manufactured generator / motor sample, determines whether the accuracy for the manufactured generator / motor sample is within a preset reference value, and, when the accuracy for the manufactured generator / motor sample is within the preset reference value as a result of the determination, manufactures a prototype based on the predicted structural specifications of the corresponding generator / motor related to the manufactured generator / motor sample in conjunction with a generator / motor production device.

[0006] As an example related to the present invention, the reverse engineering input data of the generator / motor may include the rotor size, voltage, current, magnetic force of magnets, type of stator material, and RPM related to the generator / motor that the user wishes to predict, and the predicted structural specifications of the generator / motor may include the magnet area, the number of magnets, the distance between magnets, the skew angle, the stator size, the number of coils, the coil height, the number of coil turns, the coil area, and the reverse engineering input data of the generator / motor.

[0007] An artificial intelligence-based generator / motor design method according to an embodiment of the present invention may include: a step of predicting, by a control unit, predicted structural specifications of a generator / motor by applying a genetic algorithm based on reverse engineering input data of a generator / motor according to a user input and performance evaluation data for each structural variable data of a plurality of generators / motors generated in advance; a step of manufacturing, by the control unit, a generator / motor sample based on the predicted structural specifications of the generator / motor in conjunction with a 3D printer; a step of calculating, by the control unit, an accuracy of the manufactured generator / motor sample; a step of determining, by the control unit, whether the accuracy of the manufactured generator / motor sample is within a preset reference value; and a step of manufacturing, by the control unit, a prototype based on the predicted structural specifications of the corresponding generator / motor related to the manufactured generator / motor sample, in conjunction with a generator / motor production device when the accuracy of the manufactured generator / motor sample is within the preset reference value as a result of the determination.

[0008] As an example related to the present invention, the method may further include a step of generating structural variable data of a plurality of generators / motors by the control unit; and a step of performing artificial intelligence-based machine learning based on the structural variable data of the plurality of generators / motors by the control unit, and generating performance evaluation data for each structural variable data of the plurality of generators / motors based on the machine learning results.

[0009] As an example related to the present invention, the step of generating structural variable data of the plurality of generators / motors may include a step of generating pre-design conditions of the plurality of generators / motors by utilizing a design of experiments method; a step of extracting performance results of the plurality of generators / motors through simulation based on the pre-design conditions of the plurality of generators / motors; and a step of preprocessing data before artificial intelligence learning for the plurality of pre-design conditions based on the extracted performance results of the plurality of generators / motors to generate structural variable data of the plurality of different generators / motors.

[0010] As an example related to the present invention, the process of extracting the performance result values ​​of the plurality of generators / motors can extract the performance result values ​​of the plurality of generators / motors for the plurality of pre-design conditions through a finite element analysis simulation based on Maxwell's equations.

[0011] As an example related to the present invention, the process of preprocessing data before artificial intelligence learning for a plurality of pre-design conditions based on the plurality of extracted generator / motor performance result values ​​and generating structural variable data of the plurality of different generators / motors can include: checking, among the plurality of pre-design conditions of the plurality of generators / motors based on the plurality of extracted generator / motor performance result values ​​and the preset generator / motor performance reference values, at least one pre-design condition of the generator / motor corresponding to at least one generator / motor performance result value that satisfies the preset generator / motor performance reference value.

[0012] The present invention generates structural variable data of a plurality of generators / motors, performs artificial intelligence-based machine learning based on the generated structural variable data of the plurality of generators / motors, generates performance evaluation data for each structural variable data of the plurality of generators / motors based on the results of the machine learning, applies a genetic algorithm based on reverse engineering input data of the generator / motor according to user input and the previously generated performance evaluation data for each structural variable data of the plurality of generators / motors to predict the structural specifications of the generator / motor, evaluates the performance of a sample manufactured through 3D printing based on the predicted structural specifications of the generator / motor, and manufactures a prototype based on the results of the performance evaluation, thereby reducing the cost and time incurred in actual experiments, and enabling the manufacture of a variety of generators / motors based on artificial intelligence.

[0013] Figure 1 is a block diagram showing the configuration of an artificial intelligence-based generator / motor design device according to an embodiment of the present invention.

[0014] Figure 2 is a flowchart illustrating an artificial intelligence-based generator / motor design method according to an embodiment of the present invention.

[0015] FIG. 3 is a diagram showing an example of pre-design conditions of a generator / motor according to an embodiment of the present invention.

[0016] FIG. 4 is a diagram showing an example of performance results corresponding to pre-design conditions of a generator / motor according to an embodiment of the present invention.

[0017] It should be noted that the technical terms used in the present invention are used merely to describe specific embodiments and are not intended to limit the present invention. Furthermore, unless specifically defined otherwise herein, the technical terms used herein should be interpreted as having a meaning generally understood by those skilled in the art to which the present invention pertains, and should not be interpreted in an overly comprehensive or overly narrow sense. Furthermore, if a technical term used herein is incorrect and fails to accurately express the spirit of the present invention, it should be replaced with a technical term that can be correctly understood by those skilled in the art. Furthermore, general terms used herein should be interpreted according to their dictionary definitions or according to the context, and should not be interpreted in an overly narrow sense.

[0018] Additionally, singular expressions used in the present invention include plural expressions unless the context clearly dictates otherwise. Terms such as "consist of" or "include" in the present invention should not necessarily be construed to include all of the components or steps described in the invention, and should be construed to mean that some of the components or steps may not be included, or that additional components or steps may be included.

[0019] Additionally, terms including ordinal numbers, such as "first" and "second," used in the present invention may be used to describe components, but the components should not be limited by these terms. The terms are used solely to distinguish one component from another. For example, without departing from the scope of the present invention, a first component could be referred to as a second component, and similarly, a second component could also be referred to as a first component.

[0020] Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the attached drawings. Regardless of the drawing numbers, identical or similar components are given the same reference numbers and redundant descriptions thereof will be omitted.

[0021] Furthermore, when describing the present invention, detailed descriptions of related known technologies will be omitted if they are deemed to obscure the gist of the present invention. Furthermore, it should be noted that the attached drawings are intended solely to facilitate understanding of the spirit of the present invention and should not be construed as limiting the spirit of the present invention.

[0022] FIG. 1 is a block diagram showing the configuration of an artificial intelligence-based generator / motor design device (100) according to an embodiment of the present invention.

[0023] As illustrated in FIG. 1, the AI-based generator / motor design device (100) is composed of a communication unit (110), a storage unit (120), a display unit (130), a voice output unit (140), and a control unit (150). Not all components of the AI-based generator / motor design device (100) illustrated in FIG. 1 are essential components, and the AI-based generator / motor design device (100) may be implemented with more components than the components illustrated in FIG. 1, or may be implemented with fewer components.

[0024] The above artificial intelligence-based generator / motor design device (100) is applicable to various devices such as a smart phone, a portable terminal, a mobile terminal, a foldable terminal, a personal digital assistant (PDA), a portable multimedia player (PMP) terminal, a telematics terminal, a navigation terminal, a personal computer, a notebook computer, a slate PC, a tablet PC, an ultrabook, a wearable device (e.g., a smartwatch, a smart glass, a head mounted display (HMD), etc.), a Wibro terminal, an IPTV (Internet Protocol Television) terminal, a smart TV, a digital broadcasting terminal, an audio video navigation (AVN) terminal, an audio / video (A / V) system, a flexible terminal, a digital signage device, an artificial intelligence speaker, etc. Can be applied to terminals.

[0025] The above communication unit (110) communicates with any internal component or at least one external terminal via a wired / wireless communication network. At this time, the external terminal may include a 3D printer (not shown), a generator / motor production device (not shown), a server (not shown), another terminal (not shown), etc. Here, wireless Internet technologies include Wireless LAN (WLAN), Digital Living Network Alliance (DLNA), Wireless Broadband (Wibro), World Interoperability for Microwave Access (Wimax), High Speed ​​Downlink Packet Access (HSDPA), High Speed ​​Uplink Packet Access (HSUPA), IEEE 802.16, Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A), Wireless Mobile Broadband Service (WMBS), etc., and the communication unit (110) transmits and receives data according to at least one wireless Internet technology within a range including Internet technologies not listed above. Additionally, short-range communication technologies may include Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, Near Field Communication (NFC), Ultra Sound Communication (USC), Visible Light Communication (VLC), Wi-Fi, and Wi-Fi Direct.Additionally, wired communication technologies may include Power Line Communication (PLC), USB communication, Ethernet, serial communication, and optical / coaxial cables.

[0026] In addition, the communication unit (110) can mutually transmit information to any terminal via a universal serial bus (USB).

[0027] In addition, the communication unit (110) transmits and receives wireless signals with a base station, the 3D printer, the generator / motor production device, the server, the other terminals, etc. on a mobile communication network constructed according to technical standards or communication methods for mobile communication (e.g., GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), CDMA2000 (Code Division Multi Access 2000), EV-DO (Enhanced Voice-Data Optimized or Enhanced Voice-Data Only), WCDMA (Wideband CDMA), HSDPA (High Speed ​​Downlink Packet Access), HSUPA (High Speed ​​Uplink Packet Access), LTE (Long Term Evolution), LTE-A (Long Term Evolution-Advanced), etc.).

[0028] In addition, the communication unit (110) transmits a control signal for producing a generator / motor sample to the 3D printer under the control of the control unit (150), or transmits another control signal for producing a generator / motor prototype to the generator / motor production device.

[0029] The above storage unit (120) stores various user interfaces (UI), graphical user interfaces (GUI), etc.

[0030] In addition, the storage unit (120) stores data and programs necessary for the operation of the artificial intelligence-based generator / motor design device (100).

[0031] That is, the storage unit (120) can store a plurality of application programs (or applications) run in the artificial intelligence-based generator / motor design device (100), data for the operation of the artificial intelligence-based generator / motor design device (100), and commands. At least some of these application programs can be downloaded from an external server via wireless communication. In addition, at least some of these application programs can exist on the artificial intelligence-based generator / motor design device (100) from the time of shipment for the basic functions of the artificial intelligence-based generator / motor design device (100). Meanwhile, the application programs can be stored in the storage unit (120), installed in the artificial intelligence-based generator / motor design device (100), and driven by the control unit (150) to perform the operation (or function) of the artificial intelligence-based generator / motor design device (100).

[0032] In addition, the storage unit (120) may include at least one storage medium among a Flash Memory Type, a Hard Disk Type, a Multimedia Card Micro Type, a memory of a card type (e.g., an SD or XD memory, etc.), a magnetic memory, a magnetic disk, an optical disk, a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read-Only Memory (ROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), and a Programmable Read-Only Memory (PROM). In addition, the artificial intelligence-based generator / motor design device (100) may operate a web storage that performs the storage function of the storage unit (120) on the Internet, or may operate in relation to the web storage.

[0033] In addition, the storage unit (120) stores, under the control of the control unit (150), a control signal for manufacturing a generator / motor sample, another control signal for manufacturing a generator / motor prototype, etc.

[0034] The above display unit (or display unit) (130) can display various contents, such as various menu screens, using the user interface and / or graphical user interface stored in the storage unit (120) under the control of the control unit (150). Here, the contents displayed on the display unit (130) include various text or image data (including various information data) and menu screens including data such as icons, list menus, and combo boxes. In addition, the display unit (130) may be a touch screen.

[0035] In addition, the display unit (130) may include at least one of a liquid crystal display (LCD), a thin film transistor liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), a flexible display, a 3D display, an e-ink display, and a light emitting diode (LED).

[0036] In addition, the display unit (130) displays a control signal for manufacturing a generator / motor sample, another control signal for manufacturing a generator / motor prototype, etc., under the control of the control unit (150).

[0037] The above voice output unit (140) outputs voice information included in a signal processed by the control unit (150). Here, the voice output unit (140) may include a receiver, a speaker, a buzzer, etc.

[0038] Additionally, the voice output unit (140) outputs the guidance voice generated by the control unit (150).

[0039] In addition, the voice output unit (140) outputs voice information (or sound information) corresponding to a control signal for producing a generator / motor sample, another control signal for producing a generator / motor prototype, etc., under the control of the control unit (150).

[0040] The above control unit (controller, or MCU (microcontroller unit) (150) executes the overall control function of the artificial intelligence-based generator / motor design device (100).

[0041] In addition, the control unit (150) executes the overall control function of the artificial intelligence-based generator / motor design device (100) using the program and data stored in the storage unit (120). The control unit (150) may include RAM, ROM, CPU, GPU, and a bus, and the RAM, ROM, CPU, GPU, etc. may be connected to each other through a bus. The CPU may access the storage unit (120) and perform booting using the O / S stored in the storage unit (120), and may perform various operations using various programs, contents, data, etc. stored in the storage unit (120).

[0042] In addition, the control unit (150) utilizes the structural variable data of a plurality of generators / motors (or the pre-design conditions of a plurality of generators / motors) collected in advance as data for continuous machine learning (or deep learning). Here, the input data set for the machine learning can perform training and testing functions by dividing the structural variable data of the plurality of generators / motors (or the pre-design conditions of a plurality of generators / motors) into a training set and a test set at a preset ratio (e.g., including 7:3, 8:2, etc.). In addition, the input data set for the machine learning includes the structural variable data of the plurality of generators / motors (or the pre-design conditions of a plurality of generators / motors) collected later. In addition, the output data set for the machine learning includes performance evaluation data for each structural variable data of the plurality of generators / motors, which is a part to be predicted, and is learned according to the structural variable data of the plurality of generators / motors (or the pre-design conditions of a plurality of generators / motors), and is predicted later.

[0043] That is, the control unit (150) performs a learning function to predict (or estimate / calculate / produce) performance evaluation data, etc., for structural variable data of a specific plurality of generators / motors in relation to specific raw data, etc., for a machine learning model, etc., through preset learning data. At this time, the control unit (150) stores raw data (or including structural variable data of a specific plurality of generators / motors of a component) in parallel and in a distributed manner, refines unstructured data, structured data, and semi-structured data included in the stored raw data (or including learning data, etc.), performs preprocessing including classification as metadata, performs analysis including data mining on the preprocessed data, and conducts learning, training, and testing based on at least one type of machine learning to build big data. At this time, at least one type of machine learning may be one or a combination of at least one of supervised learning, semi-supervised learning, unsupervised learning, reinforcement learning, and deep reinforcement learning. Furthermore, data mining may include performing classification, which predicts the class of new data by learning a training data set with known classes by exploring inherent relationships between preprocessed data, or clustering, which groups data based on similarity without class information.

[0044] In this way, the control unit (150) performs a learning function for the machine learning model in the form of a neural network, etc. through the learning data, etc.

[0045] Additionally, the control unit (150) generates structural variable data of multiple different generators / motors.

[0046] That is, the control unit (150) generates preliminary design conditions of a plurality of generators / motors by utilizing the design of experiments. Here, the preliminary design conditions of the generators / motors (or structural variable data of the generators / motors) include rotor size, magnet area, magnetic force of magnets, number of magnets, distance between magnets, skew angle, stator size, type of stator material, number of coils, coil height, number of coil turns, coil area, RPM (Rotations Per Minute / Revolutions Per minute), etc.

[0047] In addition, the control unit (150) extracts (or generates) performance results of the plurality of generators / motors through simulation based on the pre-design conditions of the plurality of generators / motors.

[0048] That is, the control unit (150) extracts (or generates / obtains) a plurality of generator / motor performance result values ​​for a plurality of generator / motor structures (or pre-design conditions of a plurality of generators / motors) through a finite element analysis (FEM) simulation based on Maxwell's equations. At this time, the control unit (150) may also extract (or generate / obtain) a plurality of generator / motor performance result values ​​for each of the plurality of generator / motor structures using a test generator / motor sample manufactured based on the pre-design conditions of the plurality of generators / motors.

[0049] In addition, the control unit (150) preprocesses (or processes) data before artificial intelligence learning for a plurality of pre-design conditions based on the extracted (or generated / obtained) plurality of generator / motor performance result values, thereby generating structural variable data of the plurality of different generators / motors.

[0050] That is, the control unit (150) checks (or filters) at least one pre-design condition of a generator / motor (or structural variable data of the plurality of different generators / motors) corresponding to at least one generator / motor performance result value that satisfies (or satisfies) the preset generator / motor performance reference value among the plurality of pre-design conditions of the generators / motors based on the extracted (or generated / obtained) plurality of generator / motor performance result values ​​and the preset generator / motor performance reference value, and stores the at least one pre-design condition of a generator / motor (or structural variable data of the plurality of different generators / motors) corresponding to the at least one confirmed generator / motor performance result value in the storage unit (120).

[0051] At this time, the control unit (150) checks (or filters) at least one pre-design condition of the generator / motor corresponding to at least one generator / motor performance result value that satisfies (or satisfies) the preset generator / motor performance reference value among the pre-design conditions of the plurality of generators / motors (or the plurality of generator / motor performance result values ​​corresponding to the pre-design conditions of the plurality of generators / motors).

[0052] In addition, the control unit (150) outputs structural variable data of the plurality of different generators / motors generated through the display unit (130) and / or the voice output unit (140).

[0053] In addition, the control unit (150) performs artificial intelligence-based machine learning (artificial neural network / deep learning) based on the structural variable data of the plurality of generators / motors (or the structural variable data of at least one / a plurality of generators / motors that meet the preset generator / motor performance reference value), and generates (or predicts / classifies / confirms) performance evaluation data for each structural variable data of the plurality of generators / motors based on the machine learning results. Here, the performance evaluation data includes the rotational speed, voltage, current, power, cogging torque, etc. related to the corresponding generator / motor.

[0054] That is, the control unit (150) performs machine learning (or artificial intelligence / deep learning) using the structural variable data of the plurality of generators / motors (or the structural variable data of at least one / a plurality of generators / motors that satisfy the preset generator / motor performance reference value) as input values ​​of a preset artificial intelligence-based machine learning model, and generates (or predicts / classifies / confirms) performance evaluation data for each structural variable data of the plurality of generators / motors based on the machine learning result (or the artificial intelligence result / deep learning result). Here, the machine learning model includes a linear regression model, a polynomial regression model, a support vector regression model, a logistic regression model, a decision trees model, a random forests model, a support vector machines model, etc. At this time, the machine learning model may use an artificial neural network algorithm and K-fold cross validation for learning reliability.

[0055] In this way, the control unit (150) can perform learning through artificial intelligence on the pre-design conditions of a plurality of generators / motors (or the structural variable data of a plurality of generators / motors), thereby securing (or obtaining) performance evaluation data for each pre-design condition of a plurality of generators / motors (or the performance evaluation data for each structural variable data of a plurality of generators / motors).

[0056] In addition, the control unit (150) outputs performance evaluation data (or performance evaluation data for each structural variable data of the plurality of generators / motors) according to the pre-design conditions of the plurality of generators / motors secured through the display unit (130) and / or the voice output unit (140), or stores the data in the storage unit (120).

[0057] In addition, the control unit (150) applies a genetic algorithm based on the reverse engineering input data of the generator / motor according to the user input (or the user touch / selection / control) and the performance evaluation data for each structural variable data of the plurality of generators / motors previously generated to predict (or generate) the predicted structural specifications of the generator / motor. Here, the reverse engineering input data of the generator / motor includes the rotor size, voltage, current, magnetic force of the magnet, type of stator material, RPM, etc. related to the generator / motor that the user wants to predict. In addition, the predicted structural specifications of the generator / motor (or predicted structural variable data of the generator / motor) include the magnet area, the number of magnets, the distance between magnets, the skew angle, the stator size, the number of coils, the coil height, the number of coil turns, the coil area, etc., and the reverse engineering input data of the generator / motor according to the user input.

[0058] That is, the control unit (150) predicts (or generates) the predicted structural specifications of the generator / motor by applying the reverse engineering input data of the generator / motor according to the user input (or the user touch / selection / control) and the performance evaluation data according to the structural variable data of the plurality of generators / motors previously generated to the genetic algorithm in order to confirm the optimal structural variable data of the generator / motor based on the reverse engineering input data of the generator / motor according to the user input among the performance evaluation data according to the structural variable data of the plurality of generators / motors acquired through learning by artificial intelligence.

[0059] In addition, the control unit (150) outputs reverse engineering input data of the generator / motor according to the user input, predicted structural specifications of the predicted (or generated) generator / motor, etc., through the display unit (130) and / or the voice output unit (140).

[0060] In addition, the control unit (150) operates in conjunction with a 3D printer (not shown) to produce (or configure / manufacture) a generator / motor sample based on the predicted structural specifications of the generator / motor.

[0061] Additionally, the control unit (150) calculates (or calculates / generates) accuracy for the fabricated (or constructed / manufactured) generator / motor sample.

[0062] That is, the control unit (150) compares the structural specifications for the manufactured (or configured / manufactured) generator / motor sample with the predicted structural specifications of the generator / motor, and calculates (or calculates / generates) the accuracy for the generator / motor sample.

[0063] In addition, the control unit (150) determines (or confirms) whether the accuracy of the manufactured generator / motor sample is within a preset reference value (e.g., accuracy 5%) (or whether the accuracy of the manufactured generator / motor sample is within a preset reference range).

[0064] That is, the control unit (150) determines (or confirms) whether the accuracy of the manufactured generator / motor sample is within the preset reference value (e.g., accuracy 5%) (or whether the accuracy of the manufactured generator / motor sample is included in the preset reference range) in order to confirm whether the manufactured generator / motor sample is suitable for manufacturing a prototype.

[0065] If, as a result of the judgment (or the confirmation), the accuracy of the manufactured generator / motor sample is equal to or greater than the preset reference value (e.g., accuracy 5%) (or if the accuracy of the manufactured generator / motor sample is not included in / out of the preset reference range), the control unit (150) discards (or deletes) the predicted structural specifications of the generator / motor corresponding to the manufactured generator / motor sample. At this time, if, as a result of the judgment (or the confirmation), the accuracy of the manufactured generator / motor sample is equal to or greater than the preset reference value (e.g., accuracy 5%) (or if the accuracy of the manufactured generator / motor sample is not included in / out of the preset reference range), the control unit (150) may re-attempt the process of predicting the predicted structural specifications of the generator / motor based on the reverse engineering input data of the generator / motor according to the user input and the performance evaluation data for each structural variable data of a plurality of generators / motors previously generated. Here, the control unit (150) can be configured to predict the predicted structural specifications of a new generator / motor, excluding the predicted structural specifications of the previously predicted generator / motor, for the reverse engineering input data of the generator / motor according to the user input.

[0066] In addition, if, as a result of the judgment (or the confirmation), the accuracy of the manufactured generator / motor sample is within the preset reference value (for example, accuracy 5%) (or if the accuracy of the manufactured generator / motor sample is included in the preset reference range), the control unit (150) works in conjunction with a generator / motor production device (not shown) to manufacture (or produce) a prototype based on the predicted structural specifications of the generator / motor related to the manufactured generator / motor sample.

[0067] In addition, the control unit (150) outputs reverse engineering input data of the generator / motor according to the user input, the predicted structural specifications of the predicted (or generated) generator / motor, the accuracy of the manufactured generator / motor sample, information on whether it is above the reference value, etc., through the display unit (130) and / or the voice output unit (140).

[0068] At this time, the control unit (150) may check (or determine) whether the conditions of the manufactured generator / motor sample satisfy preset reference conditions (or reference conditions / standard design guidelines according to the intended use) in order to secure the preset safety and performance of the manufactured generator / motor sample. Here, the intended use includes steam or gas turbine-driven generators, hydraulic generators, and internal combustion engine-driven generators.

[0069] In addition, if the conditions of the manufactured generator / motor sample do not meet the preset reference conditions as a result of the above verification (or judgment), the control unit (150) discards (or deletes) the predicted structural specifications of the generator / motor corresponding to the manufactured generator / motor sample.

[0070] In addition, if the conditions of the manufactured generator / motor sample satisfy the preset reference conditions as a result of the above verification (or judgment), the control unit (150) may perform a process of determining (or confirming) whether the accuracy of the manufactured generator / motor sample is within a preset reference value (for example, accuracy 5%), or may perform a process of manufacturing (or producing) a prototype based on the predicted structural specifications of the generator / motor related to the manufactured generator / motor sample in conjunction with the generator / motor production device.

[0071] In addition, the control unit (150) performs other machine learning (artificial neural network / deep learning) based on artificial intelligence on the size, specifications, arrangement status, etc. of one or more components (or parts) included in the manufactured generator / motor sample, and generates (or predicts / classifies / confirms) the suitability for the size, specifications, arrangement status, etc. of the components related to the generator / motor sample based on the other machine learning results.

[0072] In addition, if the suitability of the size, specifications, arrangement, etc. of the components related to the generated generator / motor sample is less than the preset suitability, the control unit (150) discards (or deletes) the predicted structural specifications of the generator / motor corresponding to the generated generator / motor sample.

[0073] In addition, if the suitability of the size, specifications, arrangement, etc. of the components related to the generated generator / motor sample is greater than the preset suitability, the control unit (150) may perform a process of determining (or confirming) whether the accuracy of the manufactured generator / motor sample is within a preset reference value (e.g., accuracy 5%), or may perform a process of manufacturing (or producing) a prototype based on the predicted structural specifications of the generator / motor related to the manufactured generator / motor sample in conjunction with the generator / motor production device.

[0074] In addition, the control unit (150) calculates a manufacturing cost (or manufacturing unit price) for each manufacturer in relation to one or more components (or parts) constituting the manufactured generator / motor sample, and outputs (or displays) information on the calculated manufacturing cost for each manufacturer.

[0075] In addition, the control unit (150) calculates (or outputs) energy efficiency (or energy efficiency related to the corresponding generator / motor sample) with respect to one or more components (or parts) constituting the manufactured generator / motor sample, and outputs (or displays) the calculated energy efficiency related to the corresponding generator / motor sample.

[0076] One or more functions provided in embodiments of the present invention (e.g., a function for generating structural variable data of a plurality of generators / motors, a function for learning the structural variable data of a plurality of generators / motors, a function for predicting predicted structural specifications of a generator / motor for reverse engineering input data of a generator / motor according to user input, a function for producing a sample of a generator / motor, a function for producing a prototype of a generator / motor, etc.) may be provided from a server and may be performed through a dedicated app installed in the AI-based generator / motor design device (100), a website provided by the server, etc., the function for generating structural variable data of a plurality of generators / motors, the function for learning the structural variable data of a plurality of generators / motors, the function for predicting predicted structural specifications of a generator / motor for reverse engineering input data of a generator / motor according to user input, the function for producing a sample of a generator / motor, the function for producing a prototype of a generator / motor, etc.

[0077] In this way, structural variable data of multiple generators / motors are generated, and artificial intelligence-based machine learning is performed based on the generated structural variable data of multiple generators / motors, performance evaluation data for each structural variable data of multiple generators / motors is generated based on the machine learning results, and a genetic algorithm is applied based on the reverse engineering input data of the generator / motor according to user input and the performance evaluation data for each structural variable data of multiple generators / motors generated in advance to predict the structural specifications of the generator / motor, and the performance of a sample manufactured through 3D printing based on the predicted structural specifications of the generator / motor is evaluated, and a prototype can be manufactured based on the performance evaluation results.

[0078] Hereinafter, an artificial intelligence-based generator / motor design method according to the present invention will be described in detail with reference to FIGS. 1 to 4.

[0079] Figure 2 is a flowchart illustrating an artificial intelligence-based generator / motor design method according to an embodiment of the present invention.

[0080] First, the control unit (150) generates structural variable data of multiple different generators / motors.

[0081] That is, the control unit (150) generates preliminary design conditions of a plurality of generators / motors by utilizing the design of experiments. Here, the preliminary design conditions of the generators / motors (or structural variable data of the generators / motors) include rotor size, magnet area, magnetic force of magnets, number of magnets, distance between magnets, skew angle, stator size, type of stator material, number of coils, coil height, number of coil turns, coil area, RPM (Rotations Per Minute / Revolutions Per minute), etc.

[0082] In addition, the control unit (150) extracts (or generates) performance results of the plurality of generators / motors through simulation based on the pre-design conditions of the plurality of generators / motors.

[0083] That is, the control unit (150) extracts (or generates / obtains) a plurality of generator / motor performance result values ​​for a plurality of generator / motor structures (or pre-design conditions of a plurality of generators / motors) through a finite element analysis (FEM) simulation based on Maxwell's equations. At this time, the control unit (150) may also extract (or generate / obtain) a plurality of generator / motor performance result values ​​for each of the plurality of generator / motor structures using a test generator / motor sample manufactured based on the pre-design conditions of the plurality of generators / motors.

[0084] In addition, the control unit (150) preprocesses (or processes) data before artificial intelligence learning for a plurality of pre-design conditions based on the extracted (or generated / obtained) plurality of generator / motor performance result values, thereby generating structural variable data of the plurality of different generators / motors.

[0085] That is, the control unit (150) checks (or filters) at least one pre-design condition of a generator / motor (or structural variable data of the plurality of different generators / motors) corresponding to at least one generator / motor performance result value that satisfies (or satisfies) the pre-designed generator / motor performance reference value among the plurality of pre-design conditions of the generators / motors based on the extracted (or generated / obtained) plurality of generator / motor performance result values ​​and the pre-set generator / motor performance reference value.

[0086] At this time, the control unit (150) checks (or filters) at least one pre-design condition of the generator / motor corresponding to at least one generator / motor performance result value that satisfies (or satisfies) the preset generator / motor performance reference value among the pre-design conditions of the plurality of generators / motors (or the plurality of generator / motor performance result values ​​corresponding to the pre-design conditions of the plurality of generators / motors).

[0087] For example, as illustrated in FIG. 3, the first control unit (150) generates pre-design conditions of the first generator to the pre-design conditions of the fifth generator using the experimental design method.

[0088] In addition, as illustrated in FIG. 4, the first control unit applies the finite element analysis simulation to the pre-design conditions of the first generator to the pre-design conditions of the fifth generator to generate the first generator performance result values ​​to the fifth generator performance result values, respectively.

[0089] In addition, the first control unit checks the first generator performance result value and the second generator performance result value that satisfy the preset generator performance reference value (e.g., including a reference voltage of 5 V to 30 V, a reference current of 0.25 A to 2 A, etc.) among the first to fifth generator performance result values ​​generated.

[0090] In addition, the first control unit confirms (or sets) the structural variable data of the first generator corresponding to the confirmed first generator performance result value and the structural variable data of the second generator corresponding to the confirmed second generator performance result value as data of a machine learning model by artificial intelligence (S210).

[0091] Thereafter, the control unit (150) performs artificial intelligence-based machine learning (artificial neural network / deep learning) based on the structural variable data of the plurality of generators / motors (or the structural variable data of at least one / a plurality of generators / motors that meet the preset generator / motor performance reference value), and generates (or predicts / classifies / confirms) performance evaluation data for each structural variable data of the plurality of generators / motors based on the machine learning results. Here, the performance evaluation data includes the rotational speed, voltage, current, power, cogging torque, etc. related to the generator / motor.

[0092] That is, the control unit (150) performs machine learning (or artificial intelligence / deep learning) using the structural variable data of the plurality of generators / motors (or the structural variable data of at least one / a plurality of generators / motors that satisfy the preset generator / motor performance reference value) as input values ​​of a preset artificial intelligence-based machine learning model, and generates (or predicts / classifies / confirms) performance evaluation data for each structural variable data of the plurality of generators / motors based on the machine learning result (or the artificial intelligence result / deep learning result). Here, the machine learning model includes a linear regression model, a polynomial regression analysis model, a support vector regression model, a logistic regression model, a decision tree model, a random forest model, a support vector machine model, etc. At this time, the machine learning model may also use an artificial neural network algorithm and K-fold cross-validation for learning reliability.

[0093] In this way, the control unit (150) can perform learning through artificial intelligence on the pre-design conditions of a plurality of generators / motors (or the structural variable data of a plurality of generators / motors), thereby securing (or obtaining) performance evaluation data for each pre-design condition of a plurality of generators / motors (or the performance evaluation data for each structural variable data of a plurality of generators / motors).

[0094] For example, the first control unit performs machine learning using the structural variable data of the first generator, the structural variable data of the second generator, etc., which have been confirmed as input values ​​of the machine learning model, and generates first performance evaluation data corresponding to the structural variable data of the first generator and second performance evaluation data corresponding to the structural variable data of the second generator based on the machine learning results (S220).

[0095] Thereafter, the control unit (150) applies a genetic algorithm based on the reverse engineering input data of the generator / motor according to the user input (or the user touch / selection / control) and the performance evaluation data for each structural variable data of the plurality of generators / motors previously generated to predict (or generate) the predicted structural specifications of the generator / motor. Here, the reverse engineering input data of the generator / motor includes the rotor size, voltage, current, magnetic force of the magnet, type of stator material, RPM, etc. related to the generator / motor that the user wants to predict. In addition, the predicted structural specifications of the generator / motor (or predicted structural variable data of the generator / motor) include the magnet area, the number of magnets, the distance between magnets, the skew angle, the stator size, the number of coils, the coil height, the number of coil turns, the coil area, etc., and the reverse engineering input data of the generator / motor according to the user input.

[0096] That is, the control unit (150) predicts (or generates) the predicted structural specifications of the generator / motor by applying the reverse engineering input data of the generator / motor according to the user input (or the user touch / selection / control) and the performance evaluation data according to the structural variable data of the plurality of generators / motors previously generated to the genetic algorithm in order to confirm the optimal structural variable data of the generator / motor based on the reverse engineering input data of the generator / motor according to the user input among the performance evaluation data according to the structural variable data of the plurality of generators / motors acquired through learning by artificial intelligence.

[0097] For example, the first control unit applies third generator reverse engineering input data including a third rotor size (e.g., 0.2 cm), a third voltage (e.g., 12 V), a third current (e.g., 1.2 A), a magnetic force of a third magnet (e.g., 1.2 T), a third stator material type (e.g., Fe-Si), a third RPM (e.g., 200 rpm), etc. according to user input, and performance evaluation data for each of the plurality of generator structural variable data to the genetic algorithm to predict the third generator predicted structural specifications. Here, the third generator prediction structure specifications include the third rotor size (e.g., 0.2 cm), the third voltage (e.g., 12 V), the third current (e.g., 1.2 A), the magnetic force of the third magnet (e.g., 1.2 T), the third stator material type (e.g., Fe-Si), the third RPM (e.g., 200 rpm), the third magnet area (e.g., 5.1 cm2), the third magnet number (e.g., 16), the third magnet-to-magnet distance (e.g., 0.5 cm), the third skew angle (e.g., 5°), the third stator size (e.g., 0.18 cm), the third coil number (e.g., 12), the third coil height (e.g., 12 mm), the third coil turn number (e.g., 500), the third coil area (e.g., 4.9 cm2), etc. (S230).

[0098] Thereafter, the control unit (150) works in conjunction with a 3D printer (not shown) to produce (or configure / manufacture) a generator / motor sample based on the predicted structural specifications of the generator / motor.

[0099] Additionally, the control unit (150) calculates (or calculates / generates) accuracy for the fabricated (or constructed / manufactured) generator / motor sample.

[0100] That is, the control unit (150) compares the structural specifications for the manufactured (or configured / manufactured) generator / motor sample with the predicted structural specifications of the generator / motor, and calculates (or calculates / generates) the accuracy for the generator / motor sample.

[0101] For example, the first control unit works in conjunction with the 3D printer to produce a third generator sample based on the third generator predicted structural specifications.

[0102] In addition, the first control unit compares the third structural specifications of the manufactured third generator sample with the third generator predicted structural specifications to calculate the third accuracy for the third generator sample (S240).

[0103] Thereafter, the control unit (150) determines (or confirms) whether the accuracy of the manufactured generator / motor sample is within a preset reference value (e.g., accuracy 5%) (or whether the accuracy of the manufactured generator / motor sample is within a preset reference range).

[0104] That is, the control unit (150) determines (or confirms) whether the accuracy of the manufactured generator / motor sample is within the preset reference value (e.g., accuracy 5%) (or whether the accuracy of the manufactured generator / motor sample is included in the preset reference range) in order to confirm whether the manufactured generator / motor sample is suitable for manufacturing a prototype.

[0105] For example, the first control unit determines whether the calculated third accuracy is within the preset reference value (e.g., accuracy 5%) (S250).

[0106] If, as a result of the judgment (or the confirmation), the accuracy of the manufactured generator / motor sample is equal to or greater than the preset reference value (e.g., accuracy 5%) (or if the accuracy of the manufactured generator / motor sample is not included in / out of the preset reference range), the control unit (150) discards (or deletes) the predicted structural specifications of the generator / motor corresponding to the manufactured generator / motor sample. At this time, if, as a result of the judgment (or the confirmation), the accuracy of the manufactured generator / motor sample is equal to or greater than the preset reference value (e.g., accuracy 5%) (or if the accuracy of the manufactured generator / motor sample is not included in / out of the preset reference range), the control unit (150) may re-attempt the process of predicting the predicted structural specifications of the generator / motor based on the reverse engineering input data of the generator / motor according to the user input and the performance evaluation data for each structural variable data of a plurality of generators / motors previously generated. Here, the control unit (150) can be configured to predict the predicted structural specifications of a new generator / motor, excluding the predicted structural specifications of the previously predicted generator / motor, for the reverse engineering input data of the generator / motor according to the user input.

[0107] For example, when the calculated third accuracy (e.g., 7%) is greater than the preset reference value (e.g., accuracy 5%), the first control unit discards the third generator prediction structure specification (S260).

[0108] In addition, if, as a result of the judgment (or the confirmation), the accuracy of the manufactured generator / motor sample is within the preset reference value (for example, accuracy 5%) (or if the accuracy of the manufactured generator / motor sample is included in the preset reference range), the control unit (150) works in conjunction with a generator / motor production device (not shown) to manufacture (or produce) a prototype based on the predicted structural specifications of the generator / motor related to the manufactured generator / motor sample.

[0109] For example, when the calculated third accuracy (e.g., 3%) is within the preset reference value (e.g., accuracy 5%), the first control unit, in conjunction with the generator / motor production device, manufactures a third generator prototype based on the third generator predicted structure specifications (S270).

[0110] As described above, the embodiment of the present invention generates structural variable data of a plurality of generators / motors, performs artificial intelligence-based machine learning based on the generated structural variable data of the plurality of generators / motors, generates performance evaluation data for each structural variable data of the plurality of generators / motors based on the machine learning results, applies a genetic algorithm based on reverse engineering input data of the generator / motor according to user input and the previously generated performance evaluation data for each structural variable data of the plurality of generators / motors to predict the structural specifications of the generator / motor, evaluates the performance of a sample manufactured through 3D printing based on the predicted structural specifications of the generator / motor, and manufactures a prototype based on the performance evaluation results, thereby reducing the cost and time incurred in an actual experiment, and manufacturing a variety of generators / motors based on artificial intelligence.

[0111] Those skilled in the art will appreciate that modifications and variations of the above-described content may be made without departing from the essential characteristics of the present invention. Therefore, the embodiments disclosed herein are intended to illustrate, rather than limit, the technical spirit of the present invention, and the scope of the technical spirit of the present invention is not limited by these embodiments. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included within the scope of the present invention.

[0112] The mode for carrying out the invention has been described together with the best mode for carrying out the invention above.

[0113] The present invention generates structural variable data of a plurality of generators / motors, performs artificial intelligence-based machine learning based on the generated structural variable data of the plurality of generators / motors, generates performance evaluation data for each structural variable data of the plurality of generators / motors based on the results of the machine learning, applies a genetic algorithm based on reverse engineering input data of the generator / motor according to user input and the previously generated performance evaluation data for each structural variable data of the plurality of generators / motors to predict the structural specifications of the generator / motor, evaluates the performance of a sample manufactured through 3D printing based on the predicted structural specifications of the generator / motor, and manufactures a prototype based on the results of the performance evaluation, thereby reducing the cost and time incurred in an actual experiment, and manufacturing a variety of generators / motors based on artificial intelligence, so that it has industrial applicability.

Claims

1. A storage unit that stores performance evaluation data by structural variable data of multiple generators / motors; and An artificial intelligence-based generator / motor design device, comprising: a control unit that predicts predicted structural specifications of a generator / motor by applying a genetic algorithm based on reverse engineering input data of a generator / motor according to user input and performance evaluation data for each structural variable data of the plurality of generators / motors; manufactures a generator / motor sample based on the predicted structural specifications of the generator / motor in conjunction with a 3D printer; calculates accuracy for the manufactured generator / motor sample; determines whether the accuracy of the manufactured generator / motor sample is within a preset reference value; and, when the accuracy of the manufactured generator / motor sample is within the preset reference value as a result of the determination, manufactures a prototype based on the predicted structural specifications of the corresponding generator / motor related to the manufactured generator / motor sample in conjunction with a generator / motor production device.

2. In paragraph 1, The reverse engineering input data of the above generator / motor is: Includes rotor size, voltage, current, magnetic force of magnets, type of stator material and RPM related to the generator / motor that the user wants to predict. The predicted structural specifications of the above generator / motor are: An artificial intelligence-based generator / motor design device characterized in that it includes magnet area, number of magnets, distance between magnets, skew angle, stator size, number of coils, coil height, number of coil turns, coil area, and reverse engineering input data of the generator / motor.

3. A step of predicting the predicted structural specifications of a generator / motor by applying a genetic algorithm based on the reverse engineering input data of the generator / motor according to user input and the performance evaluation data for each structural variable data of a plurality of generators / motors generated in advance by the control unit; A step of manufacturing a generator / motor sample based on the predicted structural specifications of the generator / motor by the above control unit in conjunction with a 3D printer; A step of calculating accuracy for the manufactured generator / motor sample by the above control unit; A step of determining, by the control unit, whether the accuracy of the manufactured generator / motor sample is within a preset reference value; and An artificial intelligence-based generator / motor design method, comprising a step of manufacturing a prototype based on predicted structural specifications of the generator / motor related to the manufactured generator / motor sample by the control unit in conjunction with a generator / motor production device when the accuracy of the manufactured generator / motor sample is within a preset reference value as a result of the above judgment.

4. In paragraph 3, A step of generating structural variable data of a plurality of generators / motors by the above control unit; and An artificial intelligence-based generator / motor design method characterized by further comprising a step of performing artificial intelligence-based machine learning based on the structural variable data of the plurality of generators / motors by the control unit, and generating performance evaluation data for each structural variable data of the plurality of generators / motors based on the machine learning results.

5. In paragraph 4, The step of generating the structural variable data of the above plurality of generators / motors is: The process of generating preliminary design conditions for multiple generators / motors using experimental design; A process of extracting performance results of multiple generators / motors through simulation based on the pre-design conditions of the multiple generators / motors; and An artificial intelligence-based generator / motor design method characterized by including a process of preprocessing data before artificial intelligence learning for a plurality of pre-design conditions based on the extracted plurality of generator / motor performance results, thereby generating structural variable data of the plurality of different generators / motors.

6. In paragraph 5, The process of extracting the performance results of each of the above multiple generators / motors is as follows: An artificial intelligence-based generator / motor design method characterized in that the plurality of generator / motor performance results are extracted for each of the plurality of pre-design conditions through a finite element analysis simulation based on Maxwell's equations.

7. In paragraph 5, The process of preprocessing data before artificial intelligence learning for multiple pre-design conditions based on the above-mentioned multiple generator / motor performance results and generating structural variable data of multiple different generators / motors is as follows. An artificial intelligence-based generator / motor design method characterized in that, based on the extracted plurality of generator / motor performance result values ​​and the preset generator / motor performance reference values, at least one pre-design condition of the generator / motor corresponding to at least one generator / motor performance result value that satisfies the preset generator / motor performance reference value is identified among the plurality of pre-design conditions of the generator / motor.

Images